A federated learning method, a blockchain system, and a storage medium

By combining global public-key encryption and the Paillier algorithm with threshold homomorphic encryption, along with blockchain technology, the security issues of federated learning under heterogeneous data are solved, enabling secure data sharing and model training across organizations, and ensuring data privacy and model accuracy.

CN116415693BActive Publication Date: 2026-06-12CHINA MOBILE COMM LTD RES INST +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202111649063.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-30
Publication Date
2026-06-12
Estimated Expiration
2041-12-30

AI Technical Summary

Technical Problem

In existing technologies, blockchain-based federated learning computation for heterogeneous data is untrusted, especially when modeling across organizations, it lacks security measures to protect privacy, particularly when one organization has data attributes and another has data labels, making it impossible to effectively train models.

Method used

It employs global public-key encryption and global private-key decryption, records data update values ​​and tags through the blockchain, protects data privacy by combining threshold homomorphic encryption Paillier algorithm, and implements gradient calculation and model updates through smart contracts to ensure data security and non-repudiation.

Benefits of technology

It enables secure data sharing and model training under heterogeneous data conditions, ensuring data security and reliability, while providing auditing functions and accountability mechanisms for participating parties.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a kind of federal learning method and block chain system, storage medium, comprising: the first terminal of the first organization of the first data owner uses data attribute calculated update value, after using global public key encryption, record on block chain, the second terminal of the second organization of the second data owner uses global public key encryption after data label, record on block chain;Through smart contract, the first terminal and the second terminal use global private key to the encrypted update value and label are decrypted, and gradient is calculated according to the update value and label after decryption, wherein global private key is generated and distributed to data owner by trusted authority;The first terminal and the second terminal record the gradient calculated on block chain;According to gradient, model update is executed by smart contract.The application can guarantee data security, record cannot be modified and cannot be denied.If it is found that there is a malicious participant, it can directly start accountability to it.
Need to check novelty before this filing date? Find Prior Art